Databricks Genie API MCP Server
@alexxx-db
About Databricks Genie API MCP Server
This project implements a Model Context Protocol (MCP) server that exposes Databricks Genie API capabilities as tools
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"databricks-genie-mcp": {
"command": "python",
"args": [
"server.py"
]
}
}
}Tools
8Start a new conversation in a Genie space.
Create a new message in an existing conversation.
Retrieve a message from a conversation.
Get SQL query results from a message attachment.
Execute SQL for a message query attachment.
Get details about a Genie space.
Initiate a full query result download.
Poll a message until it reaches a terminal state.
Overview
What is Databricks Genie API MCP Server?
It is a Model Context Protocol (MCP) server that exposes Databricks Genie API capabilities as tools. It enables integration of Databricks' no-code AI/BI assistant with other applications, allowing natural language querying of Databricks data through a standardized interface.
How to use Databricks Genie API MCP Server?
Install Python 3.10+, clone the repository, navigate to genie_api/, install dependencies (pip install -r requirements.txt), and configure authentication via a .env file with Databricks host and credentials (PAT or OAuth). Run python server.py locally. Then configure an MCP client like Claude Desktop to launch the server using the absolute path to server.py and the correct working directory.
Key features of Databricks Genie API MCP Server
- Expose Databricks Genie API functions as MCP tools.
- Enable natural language querying of Databricks data.
- Start and manage Genie conversations.
- Create and retrieve messages.
- Execute and fetch SQL query results from Genie.
- Secure authentication with Databricks.
Use cases of Databricks Genie API MCP Server
- Query Databricks system tables using natural language (e.g., "What was our DBU consumption last month?").
- Investigate data access logs (e.g., "Who accessed the PII table yesterday?").
- Integrate Databricks Genie assistant into custom MCP-compatible client applications.
- Automate data exploration and reporting via conversational interfaces.
FAQ from Databricks Genie API MCP Server
What are the prerequisites for using the server?
Python 3.10+, a Databricks workspace with Genie access and system tables enabled (if using them), Databricks Assistant enabled, CAN USE permission on a Pro or Serverless SQL warehouse, access to Unity Catalog data, and an MCP-compatible client (e.g., Claude Desktop).
How do I configure authentication?
Create a .env file in the genie_api/ directory with either PAT credentials (DATABRICKS_HOST, DATABRICKS_TOKEN) or OAuth with service principal (DATABRICKS_HOST, DATABRICKS_CLIENT_ID, DATABRICKS_CLIENT_SECRET). Use OAuth for production and never hardcode credentials.
How do I connect the server with Claude Desktop?
Install Claude Desktop, add a JSON entry to its mcpServers config in claude_desktop_config.json with a command (e.g., python), args (full path to server.py), and workingDirectory (full path to genie_api/ directory). Restart Claude Desktop; tools should appear under the hammer icon.
What security considerations should I keep in mind?
Never hardcode credentials; use environment variables and OAuth with service principals for production. The server runs locally with your permissions, and clients must obtain user consent before executing tools. For broader deployment, work with security/DevOps to secure hosting and credential access.
How do I troubleshoot authentication or connection issues?
Verify Databricks credentials in the .env file and required permissions. Ensure absolute paths are correct in the Claude Desktop config, and check Claude Desktop logs (~/Library/Logs/Claude/ on macOS, %APPDATA%\Claude\logs on Windows) for mcp*.log files. Try running python server.py manually from the genie_api directory to test.
Frequently asked questions
What are the prerequisites for using the server?
Python 3.10+, a Databricks workspace with Genie access and system tables enabled (if using them), Databricks Assistant enabled, CAN USE permission on a Pro or Serverless SQL warehouse, access to Unity Catalog data, and an MCP-compatible client (e.g., Claude Desktop).
How do I configure authentication?
Create a `.env` file in the `genie_api/` directory with either PAT credentials (`DATABRICKS_HOST`, `DATABRICKS_TOKEN`) or OAuth with service principal (`DATABRICKS_HOST`, `DATABRICKS_CLIENT_ID`, `DATABRICKS_CLIENT_SECRET`). Use OAuth for production and never hardcode credentials.
How do I connect the server with Claude Desktop?
Install Claude Desktop, add a JSON entry to its `mcpServers` config in `claude_desktop_config.json` with a `command` (e.g., `python`), `args` (full path to `server.py`), and `workingDirectory` (full path to `genie_api/` directory). Restart Claude Desktop; tools should appear under the hammer icon.
What security considerations should I keep in mind?
Never hardcode credentials; use environment variables and OAuth with service principals for production. The server runs locally with your permissions, and clients must obtain user consent before executing tools. For broader deployment, work with security/DevOps to secure hosting and credential access.
How do I troubleshoot authentication or connection issues?
Verify Databricks credentials in the `.env` file and required permissions. Ensure absolute paths are correct in the Claude Desktop config, and check Claude Desktop logs (`~/Library/Logs/Claude/` on macOS, `%APPDATA%\Claude\logs` on Windows) for `mcp*.log` files. Try running `python server.py` manually from the `genie_api` directory to test.
Basic information
More Developer Tools MCP servers
Sentry
modelcontextprotocolModel Context Protocol Servers
TalkToFigma
sonnylazuardiTalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
BetterBugs
BetterBugsThe BetterBugs MCP (Model Context Protocol) enables you to load BetterBugs bug reports (via report links) directly to your preferred AI Agents and developer environments with MCP Client capabilities (such as Cursor, VS C
Hello World MCP Server (Reference Extension)
anthropicsDesktop Extensions: One-click local MCP server installation in desktop apps
AptiBuild AI — Career Intelligence
ParklandBuildsAptiBuild AI MCP Server — career, labor market, and business idea intelligence for AI agents. 11 tools covering real-time FRED labor market signals, BLS wage data (126 occupations), AI-generated app ideas, career paths,
Comments